Open AccessImage Classification Algorithm Based on Improved AlexNet
Author(s) -
Shaojuan Li,
Lizhi Wang,
Jia Li,
Yuan Yao
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1813/1/012051
Subject(s) - computer science , deconvolution , pattern recognition (psychology) , image (mathematics) , layer (electronics) , set (abstract data type) , algorithm , connection (principal bundle) , artificial intelligence , contextual image classification , mathematics , chemistry , geometry , organic chemistry , programming language
Aiming at the problems that the traditional CNN has many parameters and a large proportion of fully connected parameters, a image classification method is proposed, which based on improved AlexNet. This method adds deconvolution layer to traditional AlexNet and classifies the images by full connection layer. Using Cifar-10 data set to test the classification algorithm. The results indicate that the method not only reduces the number of parameters and parameters proportion of the full connection layer, but also improves the classification accuracy compared with AlexNet.